SPB Git

Repository Public Research preview

eval-claude-sonnet-5-5.json 4.2 KB 189 lines json

1{2  "author": "claude-sonnet-5-5",3  "date": "2026-11-10T05:22:17.457Z",4  "tasks": 16,5  "accepted_without": 7,6  "accepted_with": 16,7  "rows": [8    {9      "task": "opus55-deterministic",10      "target": "claude-opus-5-5",11      "without": {12        "accepted": false,13        "status": 400,14        "message": "temperature: Extra inputs are not permitted"15      },16      "with": {17        "accepted": true18      }19    },20    {21      "task": "opus55-deep-thinking",22      "target": "claude-opus-5-5",23      "without": {24        "accepted": false,25        "status": 400,26        "message": "\"thinking.type.enabled\" is not supported for this model. Use \"thinking.type.adaptive\" and \"output_config.effort\" to control thinking behavior."27      },28      "with": {29        "accepted": true30      }31    },32    {33      "task": "sonnet55-force-tool",34      "target": "claude-sonnet-5-5",35      "without": {36        "accepted": false,37        "status": 400,38        "message": "tool_choice: type \"tool\" and \"any\" are not supported for this model."39      },40      "with": {41        "accepted": true42      }43    },44    {45      "task": "fable52-no-thinking",46      "target": "claude-fable-5-2",47      "without": {48        "accepted": false,49        "status": 400,50        "message": "temperature: Extra inputs are not permitted"51      },52      "with": {53        "accepted": true54      }55    },56    {57      "task": "sonnet55-no-thinking",58      "target": "claude-sonnet-5-5",59      "without": {60        "accepted": false,61        "status": 400,62        "message": "To turn thinking off on this model, send \"thinking\": {\"type\": \"between_tools\"} instead of {\"type\": \"disabled\"}. The model does not think before responding. The "63      },64      "with": {65        "accepted": true66      }67    },68    {69      "task": "opus55-json",70      "target": "claude-opus-5-5",71      "without": {72        "accepted": true73      },74      "with": {75        "accepted": true76      }77    },78    {79      "task": "haiku45-thinking",80      "target": "claude-haiku-4-5-20251001",81      "without": {82        "accepted": true83      },84      "with": {85        "accepted": true86      }87    },88    {89      "task": "opus46-max-effort",90      "target": "claude-opus-4-6",91      "without": {92        "accepted": true93      },94      "with": {95        "accepted": true96      }97    },98    {99      "task": "sonnet45-effort",100      "target": "claude-sonnet-4-5-20250929",101      "without": {102        "accepted": false,103        "status": 400,104        "message": "temperature: Extra inputs are not permitted"105      },106      "with": {107        "accepted": true108      }109    },110    {111      "task": "haiku55-creative",112      "target": "claude-haiku-5-5",113      "without": {114        "accepted": false,115        "status": 400,116        "message": "temperature: Extra inputs are not permitted"117      },118      "with": {119        "accepted": true120      }121    },122    {123      "task": "opus55-long-output",124      "target": "claude-opus-5-5",125      "without": {126        "accepted": true127      },128      "with": {129        "accepted": true130      }131    },132    {133      "task": "opus5-fast",134      "target": "claude-opus-5",135      "without": {136        "accepted": false,137        "status": 400,138        "message": "To use the `speed` parameter with 'claude-opus-5', send the `anthropic-beta: fast-mode-2026-02-01` header."139      },140      "with": {141        "accepted": true,142        "no_access": true,143        "status": 429144      }145    },146    {147      "task": "sonnet5-system-mid",148      "target": "claude-sonnet-5",149      "without": {150        "accepted": true151      },152      "with": {153        "accepted": true154      }155    },156    {157      "task": "opus47-plain",158      "target": "claude-opus-4-7",159      "without": {160        "accepted": true161      },162      "with": {163        "accepted": true164      }165    },166    {167      "task": "fable51-tool-json",168      "target": "claude-fable-5-1",169      "without": {170        "accepted": false,171        "status": 400,172        "message": "tool_choice: type \"tool\" and \"any\" are not supported for this model."173      },174      "with": {175        "accepted": true176      }177    },178    {179      "task": "haiku55-plain",180      "target": "claude-haiku-5-5",181      "without": {182        "accepted": true183      },184      "with": {185        "accepted": true186      }187    }188  ]189}
Files main
Menu

Theme